© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4547
    Prev
    Next
    INDEX
    Explanations

    ranging from real-time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ushal
    1.46
    ponge
    1.35
    azon
    1.31
    ῶ
    1.30
    fetchall
    1.30
    ضيف
    1.30
    uds
    1.29
    izion
    1.29
    넣
    1.27
    حاب
    1.27
    POSITIVE LOGITS
     DMP
    1.24
     Madsen
    1.03
    CPP
    1.01
     CPP
    0.96
    cjs
    0.96
     Cougars
    0.96
     SPC
    0.94
     MSS
    0.93
     sufferings
    0.92
    PPT
    0.92
    Activations Density 0.044%

    No Known Activations